Fabric Skill

Setup Check - Fabric Repository

IMPORTANT: Before using this skill, verify the Fabric repository is available:

# Check if Fabric repo exists
if [ ! -d "$HOME/.claude/skills/fabric/fabric-repo" ]; then
  echo "Fabric repository not found. Cloning..."
  cd "$HOME/.claude/skills/fabric"
  git clone https://github.com/danielmiessler/fabric.git fabric-repo
  echo "Fabric repository cloned successfully."
else
  echo "Fabric repository found at $HOME/.claude/skills/fabric/fabric-repo"
fi

If the repo doesn't exist, clone it immediately before proceeding with any pattern selection.

When to Activate This Skill

Primary Use Cases:

• "Create a threat model for..."
• "Summarize this article/video/paper..."
• "Extract wisdom/insights from..."
• "Analyze this [code/malware/claims/debate]..."
• "Improve my writing/code/prompt..."
• "Create a [visualization/summary/report]..."
• "Rate/review/judge this content..."

The Goal: Select the RIGHT pattern from 242+ available patterns based on what you're trying to accomplish.

🎯 Pattern Selection Strategy

When a user requests Fabric processing, follow this decision tree:

1. Identify Intent Category

Threat Modeling & Security:

• Threat model → createthreatmodel or createstridethreat_model
• Threat scenarios → createthreatscenarios
• Security update → createsecurityupdate
• Security rules → createsigmarules, writenucleitemplaterule, writesemgrep_rule
• Threat analysis → analyzethreatreport, analyzethreatreport_trends

Summarization:

• General summary → summarize
• 5-sentence summary → create5sentence_summary
• Micro summary → createmicrosummary or summarize_micro
• Meeting → summarize_meeting
• Paper/research → summarize_paper
• Video/YouTube → youtube_summary
• Newsletter → summarize_newsletter
• Code changes → summarizegitchanges or summarizegitdiff

Wisdom Extraction:

• General wisdom → extract_wisdom
• Article wisdom → extractarticlewisdom
• Book ideas → extractbookideas
• Insights → extractinsights or extractinsights_dm
• Main idea → extractmainidea
• Recommendations → extract_recommendations
• Controversial ideas → extractcontroversialideas

Analysis:

• Malware → analyze_malware
• Code → analyzecode or reviewcode
• Claims → analyze_claims
• Debate → analyze_debate
• Logs → analyze_logs
• Paper → analyze_paper
• Threat report → analyzethreatreport
• Product feedback → analyzeproductfeedback
• Sales call → analyzesalescall

Content Creation:

• PRD → create_prd
• Design document → createdesigndocument
• User story → createuserstory
• Visualization → createvisualization, createmermaidvisualization, createmarkmap_visualization
• Essay → write_essay
• Report finding → createreportfinding
• Newsletter entry → createnewsletterentry

Improvement:

• Writing → improve_writing
• Academic writing → improveacademicwriting
• Prompt → improve_prompt
• Report finding → improvereportfinding
• Code → review_code

Rating/Evaluation:

• AI response → rateairesponse
• Content quality → rate_content
• Value assessment → rate_value
• General judgment → judge_output

2. Execute Pattern

# Basic format
fabric [input] -p [selected_pattern]

# From URL
fabric -u "URL" -p [pattern]

# From YouTube
fabric -y "YOUTUBE_URL" -p [pattern]

# From file
cat file.txt | fabric -p [pattern]

# Direct text
fabric "your text here" -p [pattern]

📚 Pattern Categories (242 Total)

Threat Modeling & Security (15 patterns)

• createthreatmodel - General threat modeling
• createstridethreat_model - STRIDE methodology
• createthreatscenarios - Threat scenario generation
• createsecurityupdate - Security update documentation
• createsigmarules - SIGMA detection rules
• writenucleitemplate_rule - Nuclei scanner templates
• writesemgreprule - Semgrep static analysis rules
• analyzethreatreport - Threat report analysis
• analyzethreatreport_cmds - Extract commands from threat reports
• analyzethreatreport_trends - Identify threat trends
• tthreatmodel_plans - Threat model for plans
• asksecurebydesignquestions - Secure by design questions
• createnetworkthreat_landscape - Network threat landscape
• analyze_incident - Incident analysis
• analyze_risk - Risk analysis

Summarization (20 patterns)

• summarize - General summarization
• create5sentence_summary - Ultra-concise 5-line summary
• createmicrosummary - Micro summary
• create_summary - Detailed summary
• summarize_micro - Micro summarization
• summarize_meeting - Meeting notes summary
• summarize_paper - Academic paper summary
• summarize_lecture - Lecture summary
• summarize_newsletter - Newsletter summary
• summarize_debate - Debate summary
• summarize_legislation - Legislation summary
• summarizerpgsession - RPG session summary
• summarizeboardmeeting - Board meeting summary
• summarizegitchanges - Git changes summary
• summarizegitdiff - Git diff summary
• summarize_pull-requests - PR summary
• summarize_prompt - Prompt summary
• youtube_summary - YouTube video summary
• createulsummary - Unsupervised Learning summary
• createcybersummary - Cybersecurity summary

Extraction (30+ patterns)

• extract_wisdom - General wisdom extraction
• extractarticlewisdom - Article-specific wisdom
• extractbookideas - Book ideas
• extract_insights - General insights
• extractinsightsdm - Daniel Miessler style insights
• extractmainidea - Core message
• extract_recommendations - Recommendations
• extract_ideas - Ideas from content
• extract_questions - Questions raised
• extract_predictions - Predictions made
• extractcontroversialideas - Controversial points
• extractbusinessideas - Business opportunities
• extract_skills - Skills mentioned
• extract_patterns - Patterns identified
• extract_sponsors - Sponsor mentions
• extract_references - References cited
• extract_instructions - Instructions from content
• extract_jokes - Humor extraction
• extractprimaryproblem - Main problem
• extractprimarysolution - Main solution
• extractproductfeatures - Product features
• extractcoremessage - Core message
• extractalgorithmupdate_recommendations - Algorithm recommendations
• extractextraordinaryclaims - Extraordinary claims
• extractmostredeeming_thing - Most valuable aspect

Analysis (35+ patterns)

• analyze_claims - Claim analysis
• analyze_malware - Malware analysis
• analyze_code - Code analysis
• analyze_paper - Paper analysis
• analyze_logs - Log analysis
• analyze_debate - Debate analysis
• analyze_incident - Incident analysis
• analyze_comments - Comment analysis
• analyze_answers - Answer analysis
• analyzeemailheaders - Email header analysis
• analyzemilitarystrategy - Military strategy
• analyze_mistakes - Mistake analysis
• analyze_personality - Personality analysis
• analyze_presentation - Presentation analysis
• analyzeproductfeedback - Product feedback
• analyze_proposition - Proposition analysis
• analyze_prose - Prose analysis
• analyze_risk - Risk analysis
• analyzesalescall - Sales call analysis
• analyzespiritualtext - Spiritual text analysis
• analyzetechimpact - Tech impact analysis
• analyzethreatreport - Threat report analysis
• analyze_bill - Legislation analysis
• analyze_candidates - Candidate analysis
• analyzecfpsubmission - CFP submission analysis
• analyzeterraformplan - Terraform plan analysis
• analyzeinterviewertechniques - Interviewer technique analysis

Creation (50+ patterns)

• create_prd - Product Requirements Document
• createdesigndocument - Design documentation
• createuserstory - User stories
• createcodingproject - Coding project
• createcodingfeature - Code features
• createmermaidvisualization - Mermaid diagrams
• createmarkmapvisualization - Markmap mindmaps
• create_visualization - General visualizations
• createthreatmodel - Threat models
• createstridethreat_model - STRIDE threat models
• createthreatscenarios - Threat scenarios
• createreportfinding - Report findings
• createnewsletterentry - Newsletter content
• create_keynote - Keynote presentations
• createacademicpaper - Academic papers
• createflashcards - Study flashcards
• create_quiz - Quizzes
• creategraphfrom_input - Graphs
• create_tags - Content tags
• createartprompt - Art generation prompts
• create_command - CLI commands
• create_pattern - Fabric patterns
• create_logo - Logo designs
• createpodcastimage - Podcast imagery
• createsigmarules - SIGMA rules
• createvideochapters - Video chapters
• createupgradepack - Upgrade documentation

Improvement (10 patterns)

• improve_writing - General writing improvement
• improveacademicwriting - Academic writing
• improve_prompt - Prompt engineering
• improvereportfinding - Report findings
• review_code - Code review
• review_design - Design review
• refinedesigndocument - Design refinement
• humanize - Humanize AI text
• enrichblogpost - Blog enhancement
• clean_text - Text cleanup

Rating/Judgment (8 patterns)

• rateairesponse - Rate AI outputs
• rateairesult - Rate AI results
• rate_content - Rate content quality
• rate_value - Rate value proposition
• judge_output - General judgment
• labelandrate - Label and rate
• check_agreement - Agreement checking
• arbiter-evaluate-quality - Quality evaluation

🔄 Updating Patterns

The Fabric repository is included as a snapshot in ${PAI_DIR}/skills/fabric/fabric-repo/.

To update to latest patterns:

# Clone fresh Fabric repo
cd /tmp
git clone --depth 1 https://github.com/danielmiessler/fabric.git

# Copy new patterns to PAI
rm -rf ${PAI_DIR}/skills/fabric/fabric-repo
cp -r fabric ${PAI_DIR}/skills/fabric/fabric-repo

# Cleanup
rm -rf /tmp/fabric

Or install Fabric separately and use local patterns:

# If you have Fabric installed locally
go install github.com/danielmiessler/fabric@latest
fabric --updatepatterns
# Patterns will be in ~/.config/fabric/patterns/

To see all available patterns:

ls ${PAI_DIR}/skills/fabric/fabric-repo/data/patterns/
# OR from your local Fabric install:
ls ~/.config/fabric/patterns/

💡 Usage Examples

Threat Modeling:

# User: "Create a threat model for our new API"
fabric "API that handles user authentication and payment processing" -p create_threat_model

Summarization:

# User: "Summarize this blog post"
fabric -u "https://example.com/blog-post" -p summarize

# User: "Give me a 5-sentence summary"
fabric -u "https://example.com/article" -p create_5_sentence_summary

Wisdom Extraction:

# User: "Extract wisdom from this video"
fabric -y "https://youtube.com/watch?v=..." -p extract_wisdom

# User: "What are the main ideas?"
fabric -u "URL" -p extract_main_idea

Analysis:

# User: "Analyze this code for issues"
fabric "$(cat code.py)" -p analyze_code

# User: "Analyze these security claims"
fabric "security claims text" -p analyze_claims

🎯 Pattern Selection Decision Matrix

🚀 Advanced Usage

Pipe content through Fabric:

cat article.txt | fabric -p extract_wisdom
pbpaste | fabric -p summarize
curl -s "https://..." | fabric -p analyze_claims

Process YouTube videos:

# Fabric handles download + transcription + processing
fabric -y "https://youtube.com/watch?v=..." -p youtube_summary

Chain patterns (manual):

# Extract then summarize
fabric -u "URL" -p extract_wisdom > wisdom.txt
cat wisdom.txt | fabric -p create_5_sentence_summary

📖 Supplementary Resources

Full Pattern List: ls ${PAIDIR}/skills/fabric/fabric-repo/data/patterns/ Fabric Repo: ${PAIDIR}/skills/fabric/fabric-repo/ Fabric Documentation: https://github.com/danielmiessler/fabric Pattern Templates: See ${PAIDIR}/skills/fabric/fabric-repo/data/patterns/officialpattern_template/

🔑 Key Insight

The skill's value is in selecting the RIGHT pattern for the task.

When user says "Create a threat model using Fabric", your job is to:

1. Recognize "threat model" intent
2. Know available options: createthreatmodel, createstridethreatmodel, createthreat_scenarios
3. Select the best match (usually createthreatmodel unless STRIDE specified)
4. Execute: fabric "[content]" -p createthreatmodel

Not: "Here are the patterns, pick one" Instead: "I'll use createthreatmodel for this" → execute immediately